Education Information: Students launch lockdown travel guide for UK tourists  |  Leadership Instincts: Professor Nicholas Stern awarded 2020 SIEPR Prize  |  Leadership Instincts: LSE becomes the eighth full member of CIVICA  |  Education Information: Emerging trends in Higher Education examined  |  International Edu News: Delirium, rare brain inflammation and stroke linked to Covid-19  |  International Edu News: Euclid space telescope’s camera a step closer to imaging galaxies  |  International Edu News: Anna Strongman appointed new CEO of Oxford University Development  |  National Edu News: PM to dedicate to the nation the 750 MW Rewa Solar Project  |  Policy Indications: New Working Norms  |  Leadership Instincts: IIT’s Face Mask Gives a Boost to Textile Industry  |  Leadership Instincts: Imperial College Supplies Backpack Activity Kits  |  Teacher Insights: No Additional Fees for Online Learning  |  Teacher Insights: Students as Co-Developers of Content  |  National Edu News: Sun like stars in their later life hold key for Li increase in the Universe   |  Parent Interventions: New Urine Test on Threatened Miscarriage  |  
August 21, 2017 Monday 09:36:29 PM IST

Speech recognition by MS a new milestone

Technology Inceptions

San Francisco: Microsofts conversational speech recognition system -- designed to accurately recognises the words in a conversation like humans do -- has reached a 5.1 per cent error rate, its lowest so far.

This milestone means that, for the first time, a computer can recognise the words in a conversation as well as a person would.

"Our research team reached that 5.1 per cent error rate with our speech recognition system, a new industry milestone, substantially surpassing the accuracy we achieved last year," Microsoft said in a blog post late on Sunday.

Last year in October, the team from Microsoft Artificial Intelligence and Research reported a speech recognition system that makes the same or fewer errors than professional transcriptionists. The researchers had then reported a word error rate (WER) of 5.9 percent.


"Last year, Microsoft's speech and dialog research group announced a milestone in reaching human parity on the 'Switchboard' conversational speech recognition task, meaning we had created technology that recognised words in a conversation as well as professional human transcribers," said Xuedong Huang, Technical Fellow, Microsoft.

'Switchboard' is a corpus of recorded telephone conversations that the speech research community has used for more than 20 years to benchmark speech recognition systems. 

The task involves transcribing conversations between strangers discussing topics such as sports and politics. The team used "Microsoft Cognitive Toolkit 2.1" (CNTK), the most scalable deep learning software available, for exploring model architectures. 

Additionally, Microsoft's investment in cloud compute infrastructure, specifically Azure GPUs, helped improve the effectiveness and speed.


Reaching human parity with an accuracy on par with humans has been a research goal for the last 25 years. 

"Microsoft's willingness to invest in long-term research is now paying dividends for our customers in products and services such as Cortana, Presentation Translator, and Microsoft Cognitive Services," the post read. "Moving from recognising to understanding speech is the next major frontier for speech technology," the post added.

Comments